Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    include

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    图为
    -0.06
    ética
    -0.06
    ти
    -0.06
    гу
    -0.06
    徼
    -0.06
     tí
    -0.06
    逛
    -0.06
    ач
    -0.06
     concess
    -0.06
     Gram
    -0.06
    POSITIVE LOGITS
     مواقع
    0.08
    (SQL
    0.07
     misrepresented
    0.07
    的声音
    0.07
    ='../
    0.07
    /Resources
    0.06
     advances
    0.06
    .')↵↵
    0.06
    \uc
    0.06
     processing
    0.06
    Act Density 0.000%

    No Known Activations